© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 9854
    Prev
    Next
    INDEX
    Explanations

    terms related to education, particularly in the context of university and business schools

    oai_token-act-pair · gpt-3.5-turbo

    references to academic or institutional titles and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ®å®
    -0.58
     jew
    -0.55
     Rugby
    -0.52
     travelling
    -0.50
     Defence
    -0.50
    ?????-
    -0.50
    Picture
    -0.50
     Nato
    -0.49
     NRL
    -0.47
     Ronnie
    -0.47
    POSITIVE LOGITS
    .</
    0.78
    .")
    0.61
     ().
    0.59
    .*
    0.59
    )</
    0.58
    estones
    0.58
    "/>
    0.58
    .","
    0.58
     vou
    0.56
    .).
    0.56
    Activations Density 1.384%

    No Known Activations